Fast measurement partitioning algorithm for multiple extended target tracking

For tracking of multiple extended targets with unknown and varying target number, the measurements partitioning is indispensable and plays an important role in achieving good performance. However, the number of possible partitions grows very fast with the increasing of total number of measurements, which causes heavy computational burden. Thus this Letter proposes a fast measurement partitioning algorithm, in which the target predictive information is explicitly considered and used to determine the clustering centres for measurement partitioning. To guarantee its robustness, the target predictions are further modified when the target number is overestimated. This flexible strategy reduces the dependence on original predictive information and significantly improves the accuracy of partitioning results. Besides, the proposed algorithm greatly reduces the partition number by fully considering possible changes of the number of newborn targets and spawned targets. It not only eliminates unreasonable and redundant measurement partitions for tracking performance improvement, but also fits well with the tracking of newborn targets and spawned targets. Simulation results verify the benefit of what the authors proposed.